Kent Overstreet e6fab655e6 bcachefs: Avoid taking journal lock unnecessarily
Previously, any time we failed to get a journal reservation we'd retry,
with the journal lock held; but this isn't necessary given
wait_event()/wake_up() ordering.

This avoids performance cliffs when the journal starts to get backed up
and lock contention shoots up.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2024-03-10 15:34:08 -04:00
..
2024-01-11 20:11:35 -08:00
2024-02-21 08:45:07 -08:00
2024-01-11 20:11:35 -08:00
2023-10-30 09:47:13 -10:00
2023-11-07 12:11:26 -08:00
2024-02-25 09:53:13 -08:00
2023-11-07 12:11:26 -08:00
2024-02-25 02:10:32 -05:00
2023-12-29 11:58:34 -08:00
2024-01-10 17:44:36 -08:00
2024-02-07 17:48:15 +00:00
2024-01-11 20:11:35 -08:00
2024-01-10 17:44:36 -08:00
2024-02-12 07:15:45 -08:00
2024-01-10 17:44:36 -08:00
2023-10-30 09:47:13 -10:00
2024-01-06 23:49:50 +01:00
2024-01-11 10:07:29 -08:00
2024-02-16 10:20:35 +09:00
2023-12-21 13:17:54 +01:00
2023-10-30 19:28:19 -10:00
2023-10-30 19:28:19 -10:00
2024-02-09 23:31:16 -05:00
2024-01-24 13:32:29 -08:00
2024-01-11 20:11:35 -08:00
2023-12-12 14:24:14 +01:00
2024-01-11 20:00:22 -08:00
2024-01-11 20:11:35 -08:00
2024-01-19 09:10:23 -08:00
2024-01-11 20:11:35 -08:00
2024-01-19 09:10:23 -08:00
2023-11-25 02:49:43 -05:00
2024-01-08 11:11:51 -08:00
2024-01-10 17:44:36 -08:00
2024-01-08 10:57:34 -08:00
2024-01-17 13:03:37 -08:00